Storage-Free Memory Dependency Prediction

Arthur Perais 1 André Seznec 1
1 PACAP - Pushing Architecture and Compilation for Application Performance
IRISA-D3 - ARCHITECTURE, Inria Rennes – Bretagne Atlantique
Abstract : Memory Dependency Prediction (MDP) is paramount to good out-of-order performance, but decidedly not trivial as a all instances of a given static load may not necessarily depend on all instances of a given static store. As a result, for a given load, MDP should predict the exact store instruction the load depends on, and not only whether it depends on an inflight store or not, i.e., ideally, prediction should not be binary. However, we first argue that given the high degree of sophistication of modern branch predictors, the fact that a given dynamic load depends on an inflight store can be captured using the binary prediction capabilities of the branch predictor, providing coarse MDP at zero storage overhead. Second, by leveraging hysteresis counters, we show that the precise producer store can in fact be identified. This embodiment of MDP yields performance levels that are on par with state-of-the-art, and requires less than 70 additional bits of storage over a baseline without MDP at all.
Document type :
Journal articles
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01396985
Contributor : Arthur Perais <>
Submitted on : Tuesday, November 15, 2016 - 11:53:46 AM
Last modification on : Thursday, February 7, 2019 - 4:22:12 PM

File

cal_preprint.pdf
Files produced by the author(s)

Identifiers

Citation

Arthur Perais, André Seznec. Storage-Free Memory Dependency Prediction. IEEE Computer Architecture Letters, Institute of Electrical and Electronics Engineers, 2016, pp.1 - 4. ⟨10.1109/LCA.2016.2628379⟩. ⟨hal-01396985⟩

Share

Metrics

Record views

461

Files downloads

496